Intern (m/f/d) Robot Learning

The AI Teams at Agile Robots are looking for an Intern (m/f/d) Robot Learning, who will help train and evaluate machine-learning models for real robots during a six-month student internship. 

This posting is for our intern talent pool and serves as an entry point to several of our AI teams. We review applications on a rolling basis and contact you when an internship matching your profile becomes available, typically several months before its start date. We match you with a team and a project during the interview process.

Responsibilities

• Model Training: Train and fine-tune machine-learning models for robot perception, manipulation, or task planning, with guidance from the team.
• Data Preparation: Collect, clean, and annotate robot data, including demonstrations recorded on real hardware, and check that it is fit for training.
• Model Evaluation: Design and run experiments in simulation and on real robots to measure where a model works and where it fails, and document the results so others can reproduce them.
• Failure Analysis: Investigate why a model that worked in testing fails on the robot, and trace the cause to the data, the model, or the setup.
• Research Prototyping: Implement selected methods from current research papers and test whether they work on our robots.

Essential Skills

• Degree Programme: Enrolled in a Master’s programme in Computer Science, Robotics, Electrical Engineering, Mathematics, or a related field.
• Machine Learning: Hands-on experience training and evaluating neural networks in PyTorch or a comparable framework, gained through coursework, projects, or research.
• Project Experience: At least one machine-learning project in which you prepared the data and designed the evaluation yourself.
• Mathematical Foundations: Solid understanding of linear algebra, probability, and optimisation as they are used in machine learning.
• Python Programming: Working proficiency in Python for data processing, training scripts, and experiment tooling.

Beneficial Skills

• Robot Learning: Experience with imitation learning, reinforcement learning, or vision-language-action models.
• Robot Hardware: Experience running code on a physical robot or sensor setup, for example in a university lab or a student robotics team.
• Language Agents: Experience building a system in which a language model plans or triggers actions in a simulator or on a robot.
• Computer Vision: Experience with models for object detection, segmentation, or 3D perception.
• Simulation: Experience with robot simulators such as Isaac Sim, MuJoCo, or Gazebo.